Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    string formatting syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
    家
    -0.06
     mặt
    -0.06
    ^^
    -0.06
     livre
    -0.06
     швид
    -0.06
     зараз
    -0.06
    وية
    -0.06
    램
    -0.06
     近
    -0.06
    POSITIVE LOGITS
    arranty
    0.07
     forgiving
    0.07
    ITUDE
    0.06
    izacao
    0.06
    yh
    0.06
    україн
    0.06
     ell
    0.06
     lied
    0.06
     Political
    0.06
    	file
    0.06
    Act Density 0.003%

    No Known Activations